Models · Mistral
Codestral
Codestral is Mistral's specialized code generation model, fine-tuned for software development tasks. With a 256K context window, it handles large codebases and complex programming challenges at an affordable price.
Input $0.30 per 1M tokens
Output $0.90 per 1M tokens
Context 256K tokens · $1.20 combined per 1M
Key strengths
- — Purpose-built for code generation
- — Large 256K context for big codebases
- — Supports 80+ programming languages
- — Excellent cost-performance for coding
Best use cases
- Code generation and completion
- Multi-file refactoring and migration
- API and SDK development
- Technical documentation generation
Pricing details
| Input (per 1M tokens) | $0.30 |
| Output (per 1M tokens) | $0.90 |
| Context window | 256K tokens |
| Architecture | Code-specialized transformer, 256K context, trained on 80+ programming languages |
| Provider | Mistral |
Code generation specialist
Recent coverage
Mozilla's Firefox Smart Window uses Mistral AI for private browsing
Cohere's 218B Translation Model Claims to Beat Google Translate on Speed and Cost
Samsung embeds Mistral AI on-premises to boost chip yields
NVIDIA brings Rust to GPU kernels with new cuda-oxide and cutile-rs tools
Mistral raises record $3.5B as Chinese firms bypass Nvidia bans
The sharpest AI news, curated daily.
One email each morning. Summarized, sourced, and skimmable in under three minutes.
Pricing data is sourced from official API documentation and updated weekly. Actual costs may vary based on prompt caching, batch processing, service tiers, and regional pricing. Inblix is not affiliated with Mistral.